Projets novateurs réalisés

Estimation des forces musculaire lors du pédalage à bras en concentrique et en excentrique

D’après de nombreuses études, le mode de pédalage excentrique (longueur du muscle augmente durant l’effort) semble être un mode de travail intéressant pour le bas du corps, l’objectif est donc d’éclaircir la voie pour ce qui est du haut du corps. L’analyse comparative des forces musculaires permettra d’avoir une idée plus précise des atouts de chaque mode de pédalage, au long terme, cela pourrait se traduire, par exemple, par des recommandations sur des types d’exercices de réadaptation.

Développement mécanique d’une plateforme d’entraînement à résistance active

L’évaluation et la rééducation musculaire rencontrent actuellement des défis importants en termes de précision, de personnalisation et d’objectivité. Les méthodes d’évaluation traditionnelles reposent principalement sur des tests subjectifs de force statique réalisés par le physiothérapeute. Ces approches présentent plusieurs limitations : elles ne fournissent pas de données quantitatives précises et évaluent le travail musculaire uniquement en tension statique et dans une seule amplitude de mouvement.

Il est aujourd’hui reconnu que le mode de contraction excentrique — durant lequel le muscle s’allonge tout en étant sous tension — est plus efficace que le mode concentrique — où le muscle se raccourcit sous tension — pour le renforcement musculaire. Cependant, sa mise en œuvre est plus complexe, car elle exige au préalable une contraction concentrique pour charger le muscle, avant de permettre son étirement contrôlé.

Le présent projet a pour objectif le développement mécanique d’une plateforme innovante permettant de réaliser plusieurs mouvements spécifiques, ciblant différents modes de contraction musculaire. Cette plateforme est conçue pour offrir une résistance venant du bas, et permettre une exécution fluide et contrôlée de ces mouvements. Elle sera équipée d’un système capable de récupérer en temps réel des données sur l’intensité et la qualité de la contraction musculaire, afin d’optimiser l’entraînement et la rééducation.

Technical Business Intern working within cross functional teams to commercialize AI-powered solutions in the Public Services Sector

AltaML builds artificial intelligence (AI)-enabled solutions to business problems. We work with organisations, bringing together their data and domain expertise with our AI expertise, to develop AI solutions that are deployed in their operations. We also commercialize AI-enabled products business via industry-specific ventures, yielding scalability from our investment in the first solution. AltaML’s AI Lab for Government, also known as GovLab, is a talent accelerator for public service professionals, post-secondary students and recent graduates. GovLab.ai’s mission is to set a global example of how to transform the public sector through applied AI, and is designed to encourage the growth of technical and business AI skill sets that are in high demand across Alberta and around the world. AltaML’s Venture Studio is an incubator program that works with founders and co-founders in the emerging tech industry to scale ideas, build venture products, and launch AI/ML startups across numerous industries; this includes our venture partners at Brilliant Harvest (AgTech), Jurisage Group Inc. (Legal Tech), and Prevoir (Fashion Tech).
The intern listed (Rachel Wang) on this particular application will continue to work alongside the Government of Alberta team to further develop our use case labelled “Document Classification” using Machine Learning. The goal is to enable the Information Management team in the Government of Alberta to automate the labeling of hundreds of millions of documents with a document classification taxonomy based on function and activity.
? Focus: Using Object Character Recognition, and Natural Language Processing techniques along with Large Language Models, this pilot will train ML models to recommend a classification label for each document. Additional deliverables include front-end development for bulk classification, architecture design for secure training based on privacy requirements, and efficient design for cost savings at scale.
? Value: The GoA stores an estimated 500-600 million documents, many of which are unclassified. The goal of this PoC was to explore classifying documents with machine learning so they may receive an appropriate retention schedule. A machine learning solution would ensure documents are classified, making them easier to find and mitigating productivity loss. The solution would also reduce the cost of storing documents that should have been disposed of.
The intern listed (Veronica Garth) on this particular application will work alongside the Government of Alberta Health team to further develop and pilot our use case labelled “Health Demand Forecasting” using Machine Learning. The goal is to enable the Alberta Health team to accurately forecast the demand for seasonal immunizations and healthcare resources, ensuring sufficient supply coverage while minimizing waste.
? Focus: Using time series analysis, unsupervised clustering, and supervised learning techniques, this pilot will train ML models to predict the number of immunizations required based on emerging trends, seasonal outbreaks, and population health indicators. Additional deliverables include developing forecasting dashboards, designing scalable architecture for secure data handling, and optimizing the models for real-time prediction and integration with supply chain systems.
? Value: The Alberta Health system faces fluctuating demand for immunizations and medical supplies due to seasonal and demographic factors. A machine learning solution would provide accurate forecasts to support better planning and resource allocation, reducing waste and improving public health outcomes. This approach would enable proactive decision-making, ensuring Albertans have timely access to immunizations while improving efficiency across the healthcare supply chain.

A Systematic Design and Hardening of a High-Speed Transimpedance Amplifier in 65nm CMOS

High-speed communication systems used in satellites and advanced physics experiments face a significant challenge: they must be both incredibly fast and resilient enough to survive intense radiation. Often, the techniques used to make microchips radiation-proof also make them slow. This research project aims to solve this dilemma by designing a specialized microchip that acts as the “front-end” for optical signals. The central goal is to study the trade-off between speed and durability systematically. By applying state-of-the-art radiation-hardening techniques and precisely measuring their impact on performance, I will develop a clear design guide that helps future engineers build circuits that achieve the best possible balance of both. This collaboration benefits both institutions by advancing cutting-edge research at Polytechnique Montréal in electronics for harsh environments, while transferring valuable skills and knowledge back to Zewail City of Science and Technology. Crucially, it establishes a new international research partnership, paving the way for future joint projects and student exchanges.

Reinforcement Learning Based Assistive Robotic Arm Control and Path Planning Automization

This project aims to make assistive robots smarter and easier to use for people with limited mobility. Researchers will develop a new type of control system for a wheelchair-mounted robotic arm that helps users complete everyday tasks like grabbing objects, opening drawers, or pressing buttons. Using advanced artificial intelligence, the system will learn through realistic computer simulations how to adjust automatically to changes, such as different object weights or the tilt of a wheelchair, without needing manual fine-tuning. The research will be done in collaboration with Sielo Robotics, an Ottawa-based company focused on creating affordable assistive technology. The results will help Sielo improve the reliability and usability of their robotic arm, making it more adaptable for real-world use. Ultimately, this project supports greater independence for people with disabilities while strengthening Canada’s leadership in robotics and accessibility innovation.

Transportation Optimization in the Forestry Sector

The proposed research project aims to enhance transportation logistics in Quebec’s forestry sector by developing models that incorporate economic, environmental, and social factors. The intern will identify and measure key indicators, including transportation costs, CO2 emissions, and community impacts, using tools such as GIS and expert consultations. These indicators will be integrated into decision-support models to assist forestry sector in making more sustainable and efficient choices. The anticipated benefits include improved resource management, reduced environmental impact, and increased international collaboration between Canada and Mexico.

L2M – BSI Proposal Lukas Grasse

Reverb Robotics provides an end-to-end auditory awareness solution for robots, but needs to validate the industrial market for its product beyond its initial sales to research labs. This project will involve an intern participating in the Lab2Market program to perform customer discovery and test the company’s business-to-business (B2B) assumption. The intern will then work to identify and validate the most promising target customer market and develop a comprehensive sales strategy, sales deck, and business model to target this new profile. The primary benefit to Reverb Robotics will be a clear market validation and a strategic plan to acquire industrial customers, helping to launch their technology into the market.

TRLUP – Aegisnova

The Healthcare Kiosk Project aims to enhance access to timely medical care by deploying self-service, automated kiosks that enable patients to conduct virtual doctor consultations, perform basic blood tests, and collect blood samples for laboratory analysis—all without the need for an appointment. By placing these kiosks in accessible locations such as pharmacies, hospitals, and walk-in clinics, starting with five pilot units across Halifax, the project seeks to reduce clinic wait times, alleviate pressure on healthcare providers, and offer on-demand point-of-care services.

Moderniser l’évaluation foncière commerciale : modélisation des attributs, régressions quantiles spatio-temporelles et approche de nowcasting

Le projet cherche à moderniser la façon dont on évalue la valeur des immeubles commerciaux au Québec. Aujourd’hui, ces évaluations sont souvent basées sur des méthodes anciennes ou adaptées du marché résidentiel, ce qui ne reflète pas bien la réalité plus complexe du secteur commercial. L’équipe de recherche développera donc de nouveaux outils d’analyse capables de traiter automatiquement de grandes quantités de données — comme la localisation, le taux d’occupation ou la qualité des bâtiments — pour obtenir des estimations plus justes et plus réactives aux conditions du marché.

Ce projet est réalisé en partenariat avec CMSD, une entreprise québécoise spécialisée en évaluation immobilière. En combinant leur vaste base de données et des méthodes statistiques avancées, l’objectif est d’améliorer la précision, la rapidité et la fiabilité des évaluations. Ces innovations permettront à CMSD et à ses clients de mieux comprendre les dynamiques du marché et de soutenir des décisions plus éclairées en matière d’investissement et de planification urbaine.

Community Engagement Project

This project goes beyond routine marketing activities by establishing a data-driven, strategic approach to community building and social media platform engagement. The initiative will provide us with the insights, tools, and strategies needed to transform Tribe’s marketing media into an active one. By increasing engagement, we will be better positioned to deliver on Tribe’s mission of supporting racialized entrepreneurs, creating more opportunities for meaningful connections and founder-to-founder collaborations, knowledge sharing, and collaborative growth within the community.

Evaluation of Registered Nurse Prescribing in Ontario

This project, led by Women’s College Hospital’s Institute for Health System Solutions and Virtual Care (WIHV), will evaluate the implementation of Registered Nurse (RN) prescribing in Ontario. Through focus groups with prescribing and non-prescribing RNs, the project will identify barriers and enablers to adoption, as well as organizational and system-level factors influencing uptake. Findings will generate practice-based evidence to inform regulatory policy, workforce planning, and strategies to support equitable implementation of RN prescribing. This project will provide timely insights to guide policy and practice, contributing to improved access, equity, and sustainability within the health system.

Effet du type d’agent compensateur de retrait sur le comportement des mortiers à base de sable de recyclage

L’enjeu de cette recherche est double : approfondir la compréhension scientifique des mortiers intégrant des sables recyclés et adjuvants compensateurs de retrait et identifier les conditions (type et dosage d’adjuvants) permettant d’obtenir des performances comparables aux mortiers traditionnels. Le manque actuel de connaissances, combiné à la sévérité des normes en vigueur, freine encore la commercialisation de tels matériaux. Une des retombées attendues de ce projet serait de contribuer à l’intégration progressive des sables recyclés dans les référentiels normatifs, au Canada, en Europe et ailleurs dans le monde.